​
Inbound (you → the agent)

Send a photo, document, audio, or video in the private chat. The bridge downloads it into a per-turn directory and tells the harness the path. Inbound images may be plan-gated (Pro). Inbound video is still declined. See Credits. After a successful turn, downloads are deleted unless TELEKIT_DELETE_ATTACHMENTS_AFTER_TURN=0.

​
Outbound (the agent → you)

The bridged agent writes files into a per-turn outbox directory (the reply names it). Anything left there when the turn ends is delivered:
  • Images (PNG/JPEG/GIF by content, not extension) → Telegram photo, unless you force a document.
  • Video (MP4, MOV, MPEG, WebM, AVI, MKV, …) → Telegram video. Non-MP4 is transcoded with local ffmpeg when possible; otherwise sent as a file.
  • Everything else → document.
Caps: 10 files / 50 MB aggregate per turn (overridable). Overflow is reported, never silently dropped. Agent outbox delivery may be plan-gated (Premium).

​
Captions

If there is exactly one file and the text fits 1024 characters, text rides as the caption. Otherwise text goes first as its own message.

​
SVG

SVG is never sent as a photo (XML, and Telegram cannot render it as a photo). It goes as a document.